This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the masri_mt_train dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3114 | 0.1142 | 300 | 1.3081 |
| 1.1311 | 0.2283 | 600 | 1.1333 |
| 1.0435 | 0.3425 | 900 | 1.0514 |
| 1.0251 | 0.4566 | 1200 | 0.9913 |
| 1.0039 | 0.5708 | 1500 | 0.9518 |
| 0.9442 | 0.6849 | 1800 | 0.9177 |
| 0.9203 | 0.7991 | 2100 | 0.8954 |
| 0.8891 | 0.9132 | 2400 | 0.8725 |
| 0.7294 | 1.0274 | 2700 | 0.8618 |
| 0.7487 | 1.1416 | 3000 | 0.8503 |
| 0.7227 | 1.2557 | 3300 | 0.8392 |
| 0.7526 | 1.3699 | 3600 | 0.8301 |
| 0.7151 | 1.4840 | 3900 | 0.8225 |
| 0.7243 | 1.5982 | 4200 | 0.8184 |
| 0.7221 | 1.7123 | 4500 | 0.8144 |
| 0.7200 | 1.8265 | 4800 | 0.8123 |
| 0.7558 | 1.9406 | 5100 | 0.8119 |
| 0.7124 | 2.0 | 5256 | 0.8119 |
adapter_model.safetensors 148 MBtraining_args.bin 6 kBQwen/Qwen2.5-1.5B-Instruct